CtrlK
BlogDocsLog inGet started
Tessl Logo

accesslint-scan

Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.

68

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, executable, well-sequenced skill body that assumes Claude's competence and provides concrete commands with a clear audit-report-teardown workflow and validation feedback loops. No bundle files exist, and the concise section organization is appropriate for a simple skill.

DimensionReasoningScore

Conciseness

The body is lean: it assumes Claude's competence, jumps straight to executable commands and a terse report schema, and avoids explaining what WCAG or accessibility is.

3 / 3

Actionability

Provides fully executable bash commands with real flags, a concrete report structure (where/evidence/fix), and exact teardown steps — copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

The numbered Audit → Report → Tear down sequence is clear, and the re-run-to-verify feedback loop plus gotchas (exit 2 handling) provide explicit checkpoints for a fragile live-page operation.

3 / 3

Progressive Disclosure

This is a short, single-purpose skill with no external bundle files; the well-organized sections (When to Use, Audit, Report, Tear down, Gotchas, Limitations) keep everything one level deep, which scores 3 for simple skills per the rubric notes.

3 / 3

Total

12

/

12

Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A precise, distinctive description that names concrete actions and a clear niche, but it omits an explicit 'Use when' trigger clause and lacks some natural user phrasings, leaving trigger quality and completeness at the mid level.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to audit a live page for accessibility issues, find WCAG violations, or get a fix list without editing.'

Include more natural terms users say, such as 'a11y', 'screen reader compatibility', or 'ADA compliance', alongside 'WCAG violation'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'audit a live page', 'locate each WCAG violation precisely', and 'return a selector-grounded fix worklist without editing' — each names a specific deliverable rather than vague activity.

3 / 3

Completeness

It clearly states what the skill does but provides no explicit 'Use when...' trigger clause, so the 'when' guidance is only implied — capping completeness at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

Includes natural terms like 'accessibility issues', 'WCAG violation', and 'fix worklist', but lacks common user-facing phrasings such as 'a11y', 'screen reader', or 'ADA compliance' that a user might actually say.

2 / 3

Distinctiveness Conflict Risk

The audit-only / locate-don't-fix framing carves a clear niche distinct from general a11y or auditing skills, and the selector-grounded worklist language is unlikely to trigger competing skills.

3 / 3

Total

10

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/antigravity-awesome-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.